A Possibilistic Risk Assessment Framework for Unmanned Electric Vehicles With Predict of Uncertainty Traffic

At present, electric vehicles (EV) have entered a stage of rapid development. Meanwhile, with artificial intelligence (AI) technology fast improving and implementing many inventions in (EV), almost all EV sold China are equipped automatic driving to achieve safer more energy-saving driving. In order solve the problem anti-collision self-driving Smart under complex traffic, especially at intersections, most existing methods make sequential predictions for level vehicles, it becomes difficult deal sudden changes intentions other vehicles. Therefore, collision risk assessment framework based on vehicles’ trajectory prediction is proposed. The integrates solutions expected path planning, uncertainty description process, change caused by obstacle intrusion, etc., as well adopts Gaussian mixture model evaluate according probability collision. It realizes real-time evaluation makes safe decisions planning After simulation verification, effectively solves decision-making autonomous complicated traffic flow demonstrates that method better than current (SORT\Karlman filter, etc.).